Normal appearing brain white matter changes in relapsing multiple sclerosis: Texture image and classification analysis in serial MRI scans

Abstract

Objective: There is a clinical interest in identifying normal appearing white matter (NAWM) areas in brain T2-weighted (T2W) MRI scans in multiple sclerosis (MS) subjects. These areas are susceptible to disease development and areas need to be studied in order to find potential associations between texture feature changes and disease progression. Methods: The subjects investigated had a first demyelinating event (Clinically Isolated Syndrome-CIS) at baseline (Time0), and the NAWM0 (i.e. NAWM at Time0) of the brain tissue was subsequently converted to demyelinating plaques (as evaluated in a follow up MRI at Time6–12). 38 untreated subjects that had developed a CIS, had brain MRI scans within an interval of 6–12 months (Time6–12 at follow-up). An experienced MS neurologist manually delineated the demyelinating lesions at Time0 (L0) and at Time6–12 (L6–12). Areas in the Time6–12 MRI scans, where new lesions had been developed, were mapped back to their corresponding NAWM areas on the Time0 MR scans (ROIS0). In addition, contralateral ROIs of similar size and shape were segmented on the same images at Time0 (ROISC0) to form an intra-subject control group. Following that, texture features were extracted from all prescribed areas and MS lesions. Results: Texture features were used as input into Support Vector Machine (SVM) models to differentiate between the following: NAWM0 vs ROISC0, NAWM0 vs NAWM6–12, NAWM0 vs L0, NAWM6–12 vs L6–12, ROIS0 vs L0, ROIS0 vs L6–12 and ROIS0 vs ROISC0, where the corresponding % correct classifications scores were 89%, 95%, 98%, 92%, 85%, 90% and 65% respectively. Conclusions: Texture features may provide complementary information for following up the development and progression of MS disease. Future work will investigate the proposed method on more subjects.